AwareVLN：面向视觉语言导航的自感知推理
AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation
将自感知推理机制引入端到端视觉语言导航，通过结构化推理模块让模型显式理解智能体状态与任务进度，为具身智能体提供可解释的决策依据，可复用于其他需要状态感知的视觉导航任务。
原文依据 a novel framework that equips the navigation model with a self-aware reasoning mechanism
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉与语言导航（VLN）要求智能体在视觉环境中将语言指令与其自身运动进行关联。尽管最优方法利用视觉语言模型（VLM）的推理能力进行端到端动作预测，但它们往往缺乏对智能体、指令和场景之间关系的显式且可解释的理解。相反，显式构建场景地图进行启发式规划虽然直观上吸引人，但依赖于额外的3D传感器，并阻碍了大规模视觉语言预训练。为弥合这一差距，我们提出AwareVLN，一种新颖的框架，为导航模型配备自感知推理机制，使其能够以完全端到端和数据驱动的方式理解智能体状态和任务进度。我们的方法具有两项关键创新：（1）一个结构化推理模块，促进空间和任务导向的自感知；（2）一个带有进度划分的自动数据引擎，用于有效训练。在Habitat模拟器中的多个数据集上进行的大量实验表明，我们的AwareVLN显著优于之前最优的视觉语言导航方法。项目页面：https://gwxuan.github.io/AwareVLN/。
英文原文摘要 1251 字符
Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment. While state-of-the-art methods leverage the reasoning capabilities of Vision-Language Models (VLMs) for end-to-end action prediction, they often lack an explicit and explainable understanding of the relationships between the agent, the instruction, and the scene. Conversely, explicitly building a scene map for heuristic planning is intuitively appealing but relies on additional 3D sensors and hinders large-scale vision-language pre-training. To bridge this gap, we propose AwareVLN, a novel framework that equips the navigation model with a self-aware reasoning mechanism, enabling it to understand the agent's state and task progress in a fully end-to-end and data-driven manner. Our approach features two key innovations: (1) a structural reasoning module that fosters spatial and task-oriented self-awareness, and (2) an automatic data engine with progress division for effective training. Extensive experiments on various datasets in Habitat simulator show our AwareVLN significantly outperforms previous state-of-the-art vision-language navigation methods. Project page: https://gwxuan.github.io/AwareVLN/.